Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when targeting 《现代日本经济》(Contemporary Economy of Japan — 吉林大学与中华全国日本经济学会联合主办的双月刊, 1982 创刊, CSSCI) or deciding whether a Japan/East-Asia comparative-economics manuscript fits this venue. Encodes the journal's fit, 摘要≤300字/关键词5–7/参考文献≥9条顺序编码 house style, official re-check, and desk-reject heuristics.
.claude/skills/brycewang-stanford-contemporary-economy-of-japan/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 54% | 0% |
《现代日本经济》由吉林大学与中华全国日本经济学会联合创办（双月刊，1982 年创刊，CSSCI 来源期刊），是国内日本经济与中日经贸比较研究的特色刊。覆盖日本宏观经济、产业政策与企业制度、中日贸易投资与区域合作、老龄化，以及日本经验对中国改革与产业升级的启示。要求有理论框架或系统证据，避免新闻评论化。
这个 skill 是定位 / 选刊 / 改写框架工具，不替代该刊最新官方投稿须知。正式投稿前必须重新核对官网、采编系统或编辑部发布的最新模板。
chinese-review-of-financial-studies（《金融评论》） / comparative-economic-and-social-systems（《经济社会体制比较》） / contemporary-finance-and-economics（《当代财经》） / e-government（《电子政务》）。若这些刊物的读者对象更贴近，不要因为名称、地区或变量相似而强行投本刊。../../resources/source-basis.md 和 ../../resources/official-source-map.md，从其中的官方来源锚点或同一主办/出版体系入口开始核验，并在回答中说明核验日期。亚太更广议题转 asia-pacific-economic-review；国际经济理论转 journal-of-world-economy。
text【匹配度】高 / 中 / 低（一句话理由） 【目标期刊】《现代日本经济》 【选题标签】<最贴近的 2-3 个主题> 【方法证据】<当前方法是否够本刊标准> 【最大风险】<最可能导致退稿的一点> 【需核验官方要求】<投稿系统/匿名/摘要/图表/数据等> 【改投建议】<若不匹配，给出更合适期刊>
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 25,388 | 16,105 | -37% | 1 | 1 | 0% | 2,994 | 3,275 | +9% | 0 | 0 | — |
case-20 | pass→fail | 25,659 | 23,567 | -8% | 1 | 1 | 0% | 2,694 | 4,433 | +65% | 0 | 0 | — |
case-21 | pass→pass | 33,041 | 29,662 | -10% | 1 | 1 | 0% | 3,597 | 5,344 | +49% | 0 | 0 | — |
case-22 | pass→pass | 24,826 | 17,884 | -28% | 1 | 1 | 0% | 2,782 | 3,305 | +19% | 0 | 0 | — |
case-02 | fail→pass | 28,509 | 24,121 | -15% | 1 | 1 | 0% | 3,469 | 4,505 | +30% | 0 | 0 | — |
case-03 | fail→pass | 35,284 | 20,510 | -42% | 1 | 1 | 0% | 3,729 | 3,476 | -7% | 0 | 0 | — |
case-04 | fail→pass | 25,862 | 15,567 | -40% | 1 | 1 | 0% | 3,329 | 3,298 | -1% | 0 | 0 | — |
case-05 | fail→pass | 22,401 | 18,727 | -16% | 1 | 1 | 0% | 2,429 | 3,747 | +54% | 0 | 0 | — |
case-06 | fail→pass | 26,336 | 23,592 | -10% | 1 | 1 | 0% | 2,489 | 3,753 | +51% | 0 | 0 | — |
case-07 | pass→fail | 26,091 | 16,625 | -36% | 1 | 1 | 0% | 2,893 | 4,072 | +41% | 0 | 0 | — |
case-08 | pass→pass | 24,515 | 20,533 | -16% | 1 | 1 | 0% | 2,802 | 3,727 | +33% | 0 | 0 | — |
case-09 | pass→pass | 17,853 | 17,272 | -3% | 1 | 1 | 0% | 2,465 | 3,184 | +29% | 0 | 0 | — |
case-19 | pass→pass | 24,125 | 26,050 | +8% | 1 | 1 | 0% | 2,604 | 4,601 | +77% | 0 | 0 | — |
case-10 | fail→pass | 20,521 | 19,758 | -4% | 1 | 1 | 0% | 2,296 | 3,357 | +46% | 0 | 0 | — |
case-11 | pass→pass | 24,268 | 24,215 | -0% | 1 | 1 | 0% | 2,791 | 3,856 | +38% | 0 | 0 | — |
case-12 | fail→fail | 28,073 | 25,032 | -11% | 1 | 1 | 0% | 3,067 | 4,294 | +40% | 0 | 0 | — |
case-13 | fail→pass | 16,591 | 9,119 | -45% | 1 | 1 | 0% | 1,586 | 2,030 | +28% | 0 | 0 | — |
case-14 | fail→pass | 25,125 | 21,127 | -16% | 1 | 1 | 0% | 2,829 | 3,784 | +34% | 0 | 0 | — |
case-15 | fail→pass | 23,133 | 22,377 | -3% | 1 | 1 | 0% | 2,066 | 3,961 | +92% | 0 | 0 | — |
case-16 | fail→pass | 24,227 | 13,681 | -44% | 1 | 1 | 0% | 2,383 | 2,697 | +13% | 0 | 0 | — |
case-17 | fail→pass | 23,527 | 21,833 | -7% | 1 | 1 | 0% | 2,203 | 3,479 | +58% | 0 | 0 | — |
case-18 | pass→pass | 20,601 | 19,556 | -5% | 1 | 1 | 0% | 2,292 | 3,321 | +45% | 0 | 0 | — |
case-23 | fail→pass | 25,957 | 17,956 | -31% | 1 | 1 | 0% | 2,599 | 3,450 | +33% | 0 | 0 | — |
case-24 | pass→pass | 22,062 | 22,562 | +2% | 1 | 1 | 0% | 2,394 | 3,916 | +64% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted. The headline lift of +46 percentage points is the difference between those two pass rates over the 24 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.